US10839474B2 - Method and an apparatus for separating at least one object from a plurality of objects - Google Patents

Method and an apparatus for separating at least one object from a plurality of objects Download PDF

Info

Publication number
US10839474B2
US10839474B2 US15/668,224 US201715668224A US10839474B2 US 10839474 B2 US10839474 B2 US 10839474B2 US 201715668224 A US201715668224 A US 201715668224A US 10839474 B2 US10839474 B2 US 10839474B2
Authority
US
United States
Prior art keywords
area
manipulated
image
removal
process area
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
US15/668,224
Other languages
English (en)
Other versions
US20180036774A1 (en
Inventor
Tuomas Lukka
Janne KUJALA
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Mp Zenrobotics Oy
Zenrobotics Oy
Original Assignee
Zenrobotics Oy
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zenrobotics Oy filed Critical Zenrobotics Oy
Publication of US20180036774A1 publication Critical patent/US20180036774A1/en
Assigned to ZENROBOTICS OY reassignment ZENROBOTICS OY ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: KUJALA, JANNE, LUKKA, TUOMAS
Priority to US17/086,671 priority Critical patent/US11682097B2/en
Application granted granted Critical
Publication of US10839474B2 publication Critical patent/US10839474B2/en
Assigned to GENIE INDUSTRIES BV reassignment GENIE INDUSTRIES BV ASSET SALE AND PURCHASE AGREEMENT Assignors: ZENROBOTICS OY
Assigned to MP ZENROBOTICS OY reassignment MP ZENROBOTICS OY ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: GENIE INDUSTRIES B.V.
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G06T1/0014—Image feed-back for automatic industrial control, e.g. robot with camera
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
    • B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
    • B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
    • B07C5/34—Sorting according to other particular properties
    • B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
    • B07C5/3422—Sorting according to other particular properties according to optical properties, e.g. colour using video scanning devices, e.g. TV-cameras
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
    • B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
    • B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
    • B07C5/36—Sorting apparatus characterised by the means used for distribution
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J13/00—Controls for manipulators
    • B25J13/08—Controls for manipulators by means of sensing devices, e.g. viewing or touching devices
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
    • B25J19/02—Sensing devices
    • B25J19/021—Optical sensing devices
    • B25J19/023—Optical sensing devices including video camera means
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/0093—Programme-controlled manipulators co-operating with conveyor means
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/02—Programme-controlled manipulators characterised by movement of the arms, e.g. cartesian coordinate type
    • B25J9/023—Cartesian coordinate type
    • B25J9/026—Gantry-type
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1628—Programme controls characterised by the control loop
    • B25J9/163—Programme controls characterised by the control loop learning, adaptive, model based, rule based expert control
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/42—Recording and playback systems, i.e. in which the programme is recorded from a cycle of operations, e.g. the cycle of operations being manually controlled, after which this record is played back on the same machine
    • G05B19/425—Teaching successive positions by numerical control, i.e. commands being entered to control the positioning servo of the tool head or end effector
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/43—Querying
    • G06F16/432—Query formulation
    • G06F16/434—Query formulation using image data, e.g. images, photos, pictures taken by a user
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
    • G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
    • G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
    • G06K7/1404—Methods for optical code recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
    • G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
    • G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
    • G06K7/1404—Methods for optical code recognition
    • G06K7/1439—Methods for optical code recognition including a method step for retrieval of the optical code
    • G06K7/1447—Methods for optical code recognition including a method step for retrieval of the optical code extracting optical codes from image or text carrying said optical code
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
    • B25J9/1697—Vision controlled systems
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/39—Robotics, robotics to robotics hand
    • G05B2219/39106—Conveyor, pick up article, object from conveyor, bring to test unit, place it

Definitions

  • the present disclosure relates to robot systems and particularly systems wherein the robot system needs to pick objects from a plurality of objects.
  • Robot systems have widely been used in many industries to perform repetitive tasks that require little capability to actually model visually or cognitively physical objects being manipulated or that require little skill to take a hold on and to move. Robots can also be built to work in environments hostile to human floor workers or to be able to work with material hazardous to humans such as toxic or radioactive materials, waste or massive objects. It is desirable to make such robot systems as autonomous as possible to minimize the amount of human involvement needed.
  • Patent publication WO2011/161304 addresses the problem of selection of physical objects in a robot system.
  • the solution disclosed by WO2011/161304 relates to a method in which an apparatus receives first sensor data from first sensors and determines a target position from the data, the target position may be a position in space or an orientation of a gripper in a robot arm
  • First instructions are issued to the robot arm or the gripper in order to move a gripper to the target position.
  • Force feedback sensor data is received from force feedback sensors associated with either the robot arm or the gripper or from the first sensors.
  • a failure in carrying out the first instructions is determined.
  • Second sensor data is received from the at least one first sensor.
  • Successful gripping of an object is determined from the second sensor data.
  • Verification sensor data is received from at least one second sensor, in response to the determining of the successful gripping, second instructions are issued to the robot arm in order to move the arm to a predetermined position to release the grip of the gripper.
  • a problem is that the force feedback sensor provides limited information to be used as a feedback.
  • the article describes a learning-based approach to hand-eye coordination for robotic grasping from monocular images.
  • the researchers trained a large convolutional neural network to predict the probability that task-space motion of the gripper will result in successful grasps, using only monocular camera images and independently of camera calibration or the current robot pose. This requires the network to observe the spatial relationship between the gripper and objects in the scene, thus learning hand-eye coordination.
  • the researchers then use this network to servo the gripper in real time to achieve successful grasps.
  • the researchers collected over 800,000 grasp attempts over the course of two months, using between 6 and 14 robotic manipulators at any given time, with differences in camera placement and hardware. Their experimental evaluation demonstrates that their method achieves effective real-time control, can successfully grasp novel objects, and corrects mistakes by continuous servoing.
  • WO9111885 discloses an automated assembly and packaging system, wherein an apparatus and method for picking up and manipulating randomly oriented and randomly positioned objects moving on an object belt and transferring them to randomly oriented and randomly positioned destinations moving on a destination belt.
  • An image processing unit using a vision system identifies and locates objects and destinations in successive overlapping vision windows up to a predetermined optimum number of objects. The locations of those objects and destinations are entered in an output queue which is transmitted to the object and destination location queues of a first robot motion controller.
  • the first robot picks up and deposits to destinations all the objects it can in the time available while the objects and destinations pass, and enters the locations of the objects not picked up and destinations to which no object is placed in an output queue which is transmitted to the object and destination location queues of a second robot motion controller.
  • a feedback arrangement in a robot system is disclosed.
  • Feedback information is an important aspect in all machine learning systems.
  • robot systems that are picking objects from a plurality of objects this has been arranged by acquiring images of objects that have been picked.
  • images are acquired after picking they can be imaged accurately and the information about picking and also dropping success can be improved by using acquired images as a feedback in the machine learning arrangement being used for controlling the picking and dropping of objects.
  • a method for separating at least one object from a plurality of objects comprises determining, by control unit, instructions to manipulate an object in a process area and instructing a robot system comprising a manipulation element to manipulate the object in the process area.
  • the instructions further comprise information necessary to determine a removal location.
  • the method further comprises receiving at least one image of the at least one manipulated object, wherein the image is acquired after the at least one manipulated object has been removed from the process area and using the received at least one image as a feedback of the success of the manipulation and the removal at the control unit.
  • the method further comprises detecting an object in an imaging area. In another embodiment the method further comprises instructing an imaging unit to acquire an image of the object as a response to the detecting.
  • the method further comprises analyzing process area for detecting an object to be manipulated. In another embodiment the method further comprises determining the instructions based on properties of the detected object.
  • the method described above is implemented as a computer program.
  • an apparatus comprising at least one processor configured to execute computer programs and at least one memory configured to store computer programs and data for computer programs.
  • the apparatus is further connectable to external apparatuses.
  • the apparatus is further configured to perform a method described above.
  • a system comprising at least one robot configured to manipulate objects in a process area and move the objects to a removal area.
  • the system further comprises at least one imaging unit configured to acquire images of the objects and an apparatus as described above.
  • the imaging apparatus is located at the removal area.
  • the removal area is connected to a further conveyor and the imaging apparatus is configured acquire images of objects on the conveyor.
  • the imaging apparatus is configured to transmit acquired images to the apparatus.
  • the benefits of described embodiments include improvement of overall performance of a system involving picking correct objects from a process area and moving them to the correct removal area.
  • a further benefit of the described embodiments is that it is easy to add to existing robot systems and does not require changing the robot but the required imaging unit may be installed separately so that it can acquire images of picked objects and see if they are moved to the correct r area.
  • a further benefit of the described embodiments is that imaging unit and robot system do not need to be calibrated. It is sufficient that the system can keep track that the acquired images are associated with correct pick and drop procedures. However, this does not require any particular calibration.
  • FIG. 1 is a block diagram of an example embodiment of the present feedback arrangement in a robot system
  • FIG. 2 is a flow chart of an example method according to an embodiment of the present feedback arrangement in a robot system
  • FIG. 3 is a flow chart of an example method according to an embodiment of the present feedback arrangement in a robot system.
  • a robot in this context is a robot comprising grasping part, or a gripper, that is capable of picking objects from a predetermined process area and to transport them to a predetermined removal area.
  • This requirement can be fulfilled with several different types of robots, such as so-called arm robots or linear robots.
  • the feedback arrangement disclosed in the following description is suitable for all robot types.
  • Manipulation in the following description means the act the robot performs to manipulate object(s) in the process area.
  • the robot is equipped with a tool or a gripper with which it manipulates the objects.
  • Manipulation instruction in the following description means any parameters required for the manipulation of object(s) by the robot.
  • the manipulation could be gripping an object with a fingered gripper, in which case the manipulation instructions could, for example, consist of gripper opening width and the coordinates in 3d space to place the gripper to before closing the gripper, and the speed and direction to throw the object to after gripping.
  • the manipulation could alternatively be, for example, moving objects by pushing them, or gripping them with a vacuum suction gripper, or hoovering objects with a robot-moved suction pipe.
  • Process area in the following description means the area from which one robot is capable of picking objects.
  • the process area is typically limited by the reachability of the robot, however, it may also be limited by walls or other obstacles.
  • the process area in this description should be understood to be a process area for one robot.
  • the system described may have a plurality of process areas as it is obvious that a capacity of a robotic system as in the embodiments may be increased by adding more than one robot to perform the task.
  • the process area may be, for example, an area where a robot is operable and where a conveyor is passing through the process area. Thus, objects to be picked will be brought to the process area by a conveyor and the objects not picked will proceed further to the process area of a next robot or to a container in the end of the conveyor.
  • the process area includes a conveyor drop areas may be located on both sides of the conveyor.
  • the robotic system picks up an object from a process area, moves it to the drop area and drops it.
  • a drop area may be a shaft, chute or similar that is used to move the picked objects to a transportation container or further treatment. From chutes dropped object may be dropped directly to a further conveyor bringing the objects to a container or storage location or there may be container or storage location directly under the chute.
  • picking means that the intention of the robot is to move the picked object from a pickup area to a removal area.
  • the object can be removed by using various means for lifting as explained above with regard manipulation. It is not always necessary to lift the object but it can also be pulled or pushed to a removal or drop area.
  • the feedback arrangements are different embodiments of an arrangement using images of picked objects acquired by an imaging unit as a feedback for machine learning.
  • the feedback information is used to teach the system to improve the picking action and picking results.
  • FIG. 1 is a block diagram of a system using the disclosed feedback arrangement in a robot system.
  • the example of FIG. 1 is depicted from above.
  • a typical application of waste separation is illustrated.
  • the waste may be construction waste or similar waste that can be picked with a robot.
  • FIG. 1 linear robot operating on rails 10 a and 10 b disclosed.
  • a movable rail 11 On the rails, a movable rail 11 is arranged.
  • the rail 11 further comprises a grasping element 12 .
  • the grasping element 12 is movable on rail 11 .
  • the grasping element can be moved to a desired location above a conveyor 13 which is running below the level of rails 10 and 11 .
  • the distance between the level of rails and conveyor is determined by the size of objects.
  • the waste arriving at pick area below is imaged using a camera and picked in a conventional manner using the grasping element 12 .
  • the camera may be arranged to the grasping element 12 or to a fixed location so that it can be connected to controller unit 16 by fixed or wireless connection.
  • Controller 16 comprises at least one processor 17 and at least one memory.
  • the at least one processor 17 is configured to execute computer programs that are configured to control the robot arrangement 10 - 12 so that the grasping element is first moved to a correct position and then the grasping action is performed. After that the controller is configured to detect the object that was picked and decide which drop area it belongs to. Then the object is dropped in the correct drop area.
  • the at least one memory 18 is configured to store the computer programs executed by the at least one processor 16 and also data related to the computer programs being executed.
  • Drop areas may be all similar or different type depending on the application. For example, different types of drop areas may be used when the waste to be treated comprises different types of fractions that are typically different in weight or size. Furthermore, the drop area as whole may be different because of space usage requirement.
  • Drop area 14 b is a chute through which objects picked by the grasping element 12 are provided to a further conveyor 19 .
  • the conveyor 19 transports picked objects to a storage location or similar.
  • an imaging unit 15 is provided above the conveyor 19 .
  • the imaging unit 15 comprises at least one camera device for acquiring images of picked and dropped images. Because of the conveyor 19 arrangement it is possible to move objects in a manner that only one picked and dropped object is imaged at time because before the next object is dropped the previous object has already travelled further on the conveyor 19 .
  • the image acquired by imaging unit 15 is sent to the controller 16 that uses the received image as a feedback for training the learning system used for generating the picking instructions.
  • Controller 16 is using an arrangement with machine learning that may be any known machine learning arrangement.
  • machine learning may be any known machine learning arrangement.
  • commonly known methods that may be used for machine learning include naive Bayes classifiers, Bayesian networks, decision trees, random forests, gradient boosted regression trees, artificial neural networks, fuzzy logic models, probabilistic classification models.
  • a machine learning arrangement can, for example, be a machine learning method that is trained to classify candidate manipulation instructions into predetermined classes, for example likely successful or likely failing, or to output a probability that the manipulation will result in each of a set of outcomes, and the controller 16 can then use the machine learning arrangement to choose from a set of candidate manipulation instructions the instructions that are most likely to end in a desired outcome.
  • Such candidate manipulation instructions can be generated for example by generating randomized instructions, or using a simpler controller arranged to output compatible manipulation instructions.
  • the machine learning arrangement can output the manipulation instructions directly as its output, for example outputting a set of coordinates for placing a gripper to.
  • Using and training the machine learning arrangement may include calculating features associated with the manipulation instructions and the environment and using the calculated features as at least part of the input to the machine learning arrangement.
  • such features can include camera image or 3d camera image data, processed in a suitable way such as for example aligned with the robot gripper, downscaled or otherwise processed to make it suitable for the chosen machine learning arrangement, or object recognition results produced by a machine learning arrangement arranged to recognize objects or materials in an input image.
  • the robot is configured to bring the object to be dropped to an imaging zone before releasing the grip and dropping the object to a drop area.
  • a camera is configured to acquire an image to be used as a feedback.
  • the imaging zone is an area, such as a pit to which an object is dropped. After drop an image of the object is acquired. After the image is acquired the object may be, for example, pushed further to a chute or a conveyor.
  • an image of an object is acquired after the pick has been performed and the drop area has been determined.
  • the feedback information not only the success of pick but also the success of determining correct drop area is determined. This corresponds with determining the waste fraction to which the picked object belongs to.
  • the distribution of the manipulation result can also be determined, for example that the manipulation resulted in 2 objects of the correct fraction but also 1 object of a wrong fraction ending in the drop area.
  • Such manipulation may be, depending on the application of the whole system, considered a successful or a failed manipulation, however the feedback can in any case then be used in the controller 16 .
  • an image of a manipulated object is acquired. It is also possible that the acquired image does not comprise the object or no image is acquired. This can happen, for example, when the object fell from the robot during the picking action and never reached the drop area.
  • the arrangement may be used also for separating one fraction from a flow of waste and the rest of the waste is treated separately in a next phase. In such example only one drop area is needed.
  • the feedback information is used for determining if the pick was successful and if the object picked actually belongs to the drop area.
  • FIG. 2 a flow chart of a method according to the feedback arrangement is described.
  • the following method is suitable to be used with an arrangement as described in FIG. 1 , however, it is only an example.
  • the method may be used also in other arrangements that fulfill the requirements of having robotic grasping element controlled by a controller, controlling unit, server or similar, and further having an imaging unit, such as a camera, a plurality of cameras, depth camera, spectral-, infrared-, NIR-, XRF or X-ray imaging unit, imaging metal detector, or any similar imaging unit for providing feedback.
  • the method of FIG. 2 is implemented in a controller controlling the whole system.
  • the method is initiated by determining instructions for a pick, step 20 .
  • the pick area may be stationary or moving conveyor as explained above.
  • the pick area comprises different types of objects that are detected by a camera arrangement.
  • the camera arrangement acquires images and from images it is determined which object should be picked next. The decision may be done based on various variables. For example, when more than one robot is arrangement in series the picking capabilities of following robots may be taken into account because the following robots may have different properties or their drop areas are allocated to different types of objects.
  • Determined instructions include at least information on what object to pick. This may be done, for example, by instructing the picking coordinates. Picking coordinates may be changing over a time because of the movement of the conveyor and this needs to be taken into account. Instructions may also include information of the desired drop area or areas. When there are more than one suitable drop area it is possible to determine the drop area so that the following movements of the robot system are optimized.
  • Instructions are then transmitted to the robot, step 21 .
  • the instructions may be sent by the controller controlling the whole system directly to the robot making the grasp or there may be further control units in between the controller controlling the whole system and the robot.
  • the robot then receives the instructions from a controller and moves accordingly to a correct position.
  • the grasping action is performed and the target object defined by the instructions is picked.
  • the picked object is then brought to the vicinity of drop area and released so that it will drop to the drop area.
  • the object After the object has been picked it needs to be imaged. This can be done already before the object is released, for example, when the robot is near the releasing position. Other options include the released object is detected when falling to the drop area and image in the air or after it has landed to the drop area.
  • the presence of the object is detected automatically and independently from the controller where the method of FIG. 2 is performed.
  • a motion sensor or other detectors may be used to detect the object.
  • an image is acquired and it is transmitted to the controller.
  • the controller receives at least one image, step 22 and processes it as a feedback information to be used in machine learning process at the controller, step 23 .
  • FIG. 3 a method describing functionality of an overall system is described.
  • objects such as waste to be separated or sorted, is transported to the process area by conveyor or container, step 30 .
  • the objects are continuously analyzed in order to detect different object types and quantities, step 31 .
  • the pick instructions are executed by a robot with grasping element, step 33 .
  • the robot picks up the desired object and drops it to the correct drop area, step 34 .
  • an image is acquired of the object, step 35 .
  • the acquired image is then sent to a machine learning entity that is responsible for analyzing objects and determining pick instructions, step 36 .
  • the dropped object is sent to a storage location, step 37 . For example, for waiting transportation to the next location or to be transported directly to a waste processing system located in the vicinity.
  • the above mentioned method may be implemented as computer software which is executed in a computing device able to communicate with other devices.
  • the software When the software is executed in a computing device it is configured to perform the above described inventive method.
  • the software is embodied on a computer readable medium so that it can be provided to the computing device, such as the controller 16 of FIG. 1 .
  • the components of the exemplary embodiments can include computer readable medium or memories for holding instructions programmed according to the teachings of the present embodiments and for holding data structures, tables, records, and/or other data described herein.
  • Computer readable medium can include any suitable medium that participates in providing instructions to a processor for execution.
  • Computer-readable media can include, for example, a floppy disk, a flexible disk, hard disk, magnetic tape, any other suitable magnetic medium, a CD-ROM, CD ⁇ R, CD ⁇ RW, DVD, DVD-RAM, DVD ⁇ RW, DVD ⁇ R, HD DVD, HD DVD-R, HD DVD-RW, HD DVD-RAM, Blu-ray Disc, any other suitable optical medium, a RAM, a PROM, an EPROM, a FLASH-EPROM, any other suitable memory chip or cartridge, a carrier wave or any other suitable medium from which a computer can read.

Landscapes

  • Engineering & Computer Science (AREA)
  • Robotics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Electromagnetism (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Toxicology (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Automation & Control Theory (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Computing Systems (AREA)
  • Human Computer Interaction (AREA)
  • Manipulator (AREA)
  • Sorting Of Articles (AREA)
  • Processing Of Solid Wastes (AREA)
  • Specific Conveyance Elements (AREA)
US15/668,224 2016-08-04 2017-08-03 Method and an apparatus for separating at least one object from a plurality of objects Active US10839474B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/086,671 US11682097B2 (en) 2016-08-04 2020-11-02 Method and an apparatus for separating at least one object from a plurality of objects

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FI20165603 2016-08-04
FI20165603A FI127100B (fi) 2016-08-04 2016-08-04 Menetelmä ja laite vähintään yhden kappaleen erottamiseksi joukosta kappaleita

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/086,671 Continuation US11682097B2 (en) 2016-08-04 2020-11-02 Method and an apparatus for separating at least one object from a plurality of objects

Publications (2)

Publication Number Publication Date
US20180036774A1 US20180036774A1 (en) 2018-02-08
US10839474B2 true US10839474B2 (en) 2020-11-17

Family

ID=60156684

Family Applications (2)

Application Number Title Priority Date Filing Date
US15/668,224 Active US10839474B2 (en) 2016-08-04 2017-08-03 Method and an apparatus for separating at least one object from a plurality of objects
US17/086,671 Active 2038-03-17 US11682097B2 (en) 2016-08-04 2020-11-02 Method and an apparatus for separating at least one object from a plurality of objects

Family Applications After (1)

Application Number Title Priority Date Filing Date
US17/086,671 Active 2038-03-17 US11682097B2 (en) 2016-08-04 2020-11-02 Method and an apparatus for separating at least one object from a plurality of objects

Country Status (7)

Country Link
US (2) US10839474B2 (fi)
EP (1) EP3493925A4 (fi)
JP (1) JP6868684B2 (fi)
AU (1) AU2017305864A1 (fi)
CA (1) CA2974869C (fi)
FI (1) FI127100B (fi)
WO (1) WO2018024944A1 (fi)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210187735A1 (en) * 2018-05-02 2021-06-24 X Development Llc Positioning a Robot Sensor for Object Classification
US11922368B1 (en) * 2020-12-11 2024-03-05 Amazon Technologies, Inc. Object classification exception handling via machine learning

Families Citing this family (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6599827B2 (ja) * 2016-08-29 2019-10-30 ファナック株式会社 ワーク取出システム
WO2018236753A1 (en) * 2017-06-19 2018-12-27 Google Llc PREDICTION OF ROBOTIC SEIZURE USING NEURAL NETWORKS AND A GEOMETRY-SENSITIVE REPRESENTATION OF OBJECT
US11847841B2 (en) 2017-10-18 2023-12-19 Brown University Probabilistic object models for robust, repeatable pick-and-place
US11504853B2 (en) * 2017-11-16 2022-11-22 General Electric Company Robotic system architecture and control processes
SE1830136A1 (en) * 2018-04-22 2019-10-23 Zenrobotics Oy Waste Sorting Gantry Robot
SE543130C2 (en) * 2018-04-22 2020-10-13 Zenrobotics Oy A waste sorting robot gripper
US11584016B2 (en) 2018-04-24 2023-02-21 Fanuc Corporation Robot controller and system
JP6987698B2 (ja) * 2018-05-21 2022-01-05 大王製紙株式会社 選別装置、選別方法及び選別プログラム並びにコンピュータで読み取り可能な記録媒体
SE544741C2 (en) * 2018-05-11 2022-11-01 Genie Ind Bv Waste Sorting Gantry Robot and associated method
US20220137597A1 (en) * 2019-03-07 2022-05-05 Abb Schweiz Ag Method Of Controlling An Industrial System, Control System And Industrial System
US11185980B2 (en) * 2019-04-16 2021-11-30 Abb Schweiz Ag Machine learning-based systems and methods for controlling robotic object picking and placement in training and run time environments
US20210233258A1 (en) * 2020-01-28 2021-07-29 Embodied Intelligence Inc. Identifying scene correspondences with neural networks
WO2021178873A1 (en) * 2020-03-06 2021-09-10 Embodied Intelligance Inc. Imaging process for detecting failure modes
WO2021195563A1 (en) 2020-03-26 2021-09-30 Digimarc Corporation Arrangements for digital marking and reading of items, useful in recycling
CN111790638A (zh) * 2020-04-24 2020-10-20 山东潍泉电子科技有限公司 行程定位动力金属分选系统
CN112295933B (zh) * 2020-09-17 2022-03-11 东南大学 一种机器人快速分拣货物的方法
CN114310869B (zh) * 2020-09-29 2023-04-25 上海科技大学 机器人手眼标定方法、系统以及终端
SE2030327A1 (en) 2020-10-28 2021-12-21 Zenrobotics Oy Waste Sorting Robot with gripper that releases waste object at a throw position
SE544104C2 (en) * 2020-10-28 2021-12-21 Zenrobotics Oy Waste sorting robot and method for detecting faults
CN112621750B (zh) * 2020-12-07 2022-12-16 合肥阿格德信息科技有限公司 一种工业机器人自动控制系统
CA3215397A1 (en) 2021-04-16 2022-10-20 Tomas FILLER Methods and arrangements to aid recycling
WO2023067656A1 (ja) * 2021-10-18 2023-04-27 株式会社Pfu 物体処理装置
CN114193446B (zh) * 2021-11-22 2023-04-25 上海交通大学宁波人工智能研究院 一种基于形态学图像处理的闭环抓取检测方法
CN114758243B (zh) * 2022-04-29 2022-11-11 广东技术师范大学 基于补充训练与双类位置预测的茶叶采摘方法和装置

Citations (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1991011885A1 (en) 1990-01-29 1991-08-08 Technistar Corporation Automated assembly and packaging system
US5100005A (en) * 1989-08-11 1992-03-31 Plastics Recovery, Inc. Trash bags for recyclable articles and system and method for collecting recyclable waste
US5641072A (en) * 1994-04-12 1997-06-24 Kurimoto, Ltd. Method for sorting post-consumed bottles and apparatus thereof
US6008636A (en) * 1997-09-30 1999-12-28 Motorola, Inc. Test system with robot arm for delivering a device under test
EP2233400A1 (en) 2009-03-25 2010-09-29 OPM S.p.A. Packaging process and plant
WO2011161304A1 (en) 2010-06-24 2011-12-29 Zenrobotics Oy Method for the selection of physical objects in a robot system
US8474598B2 (en) * 2008-06-20 2013-07-02 Wolfgang Huber Device and method for composing packages for a packaging machine
US8577500B2 (en) 2011-02-10 2013-11-05 Seiko Epson Corporation Robot apparatus, position detecting device, position detecting program, and position detecting method
US20130343640A1 (en) * 2012-06-21 2013-12-26 Rethink Robotics, Inc. Vision-guided robots and methods of training them
US20150019391A1 (en) * 2013-06-26 2015-01-15 Amazon Technologies, Inc. Detecting item interaction and movement
US20150081090A1 (en) * 2013-09-13 2015-03-19 JSC-Echigo Pte Ltd Material handling system and method
US9082071B2 (en) 2013-11-26 2015-07-14 Canon Kabushiki Kaisha Material classification using object/material interdependence with feedback
US9227323B1 (en) * 2013-03-15 2016-01-05 Google Inc. Methods and systems for recognizing machine-readable information on three-dimensional objects
US9486926B2 (en) * 2012-02-21 2016-11-08 Amazon Technologies, Inc. System and method for automatic picking of products in a materials handling facility
US20170080566A1 (en) * 2015-09-21 2017-03-23 Amazon Technologies, Inc. Networked robotic manipulators
US9639535B1 (en) * 2015-12-16 2017-05-02 Waste Repurposing International, Inc. Waste identification systems and methods
US20170126972A1 (en) * 2015-10-30 2017-05-04 Essential Products, Inc. Imaging device and method for generating an undistorted wide view image
US20170121113A1 (en) * 2015-09-11 2017-05-04 Berkshire Grey Inc. Robotic systems and methods for identifying and processing a variety of objects
US20170174440A1 (en) * 2015-12-16 2017-06-22 Waste Repurposing International, Inc. Household Hazardous Waste Recovery
US20170225199A1 (en) * 2014-08-13 2017-08-10 Metrosense Oy Method, apparatus and system for sorting waste
US20170355078A1 (en) * 2016-06-09 2017-12-14 Shmuel Ur Innovation Ltd. System, Method and Product for Utilizing Prediction Models of an Environment
US20170369244A1 (en) * 2016-06-27 2017-12-28 Amazon Technologies, Inc. Automated item singulation
US10059005B2 (en) * 2016-06-22 2018-08-28 Quanta Storage Inc. Method for teaching a robotic arm to pick or place an object
US10322506B2 (en) * 2016-05-06 2019-06-18 Kindred Systems Inc. Systems, devices, articles, and methods for using trained robots

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
SE500076C2 (sv) * 1989-03-23 1994-04-11 Sellbergs Engineering Ab Sätt att omhänderta avfall
JP2001259536A (ja) * 2000-03-21 2001-09-25 Nkk Plant Engineering Corp 廃棄物の分別方法および分別装置
US9990685B2 (en) * 2016-03-21 2018-06-05 Recognition Robotics, Inc. Automated guidance system and method for a coordinated movement machine

Patent Citations (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5100005A (en) * 1989-08-11 1992-03-31 Plastics Recovery, Inc. Trash bags for recyclable articles and system and method for collecting recyclable waste
WO1991011885A1 (en) 1990-01-29 1991-08-08 Technistar Corporation Automated assembly and packaging system
US5641072A (en) * 1994-04-12 1997-06-24 Kurimoto, Ltd. Method for sorting post-consumed bottles and apparatus thereof
US6008636A (en) * 1997-09-30 1999-12-28 Motorola, Inc. Test system with robot arm for delivering a device under test
US8474598B2 (en) * 2008-06-20 2013-07-02 Wolfgang Huber Device and method for composing packages for a packaging machine
EP2233400A1 (en) 2009-03-25 2010-09-29 OPM S.p.A. Packaging process and plant
WO2011161304A1 (en) 2010-06-24 2011-12-29 Zenrobotics Oy Method for the selection of physical objects in a robot system
US8577500B2 (en) 2011-02-10 2013-11-05 Seiko Epson Corporation Robot apparatus, position detecting device, position detecting program, and position detecting method
US9486926B2 (en) * 2012-02-21 2016-11-08 Amazon Technologies, Inc. System and method for automatic picking of products in a materials handling facility
US20130343640A1 (en) * 2012-06-21 2013-12-26 Rethink Robotics, Inc. Vision-guided robots and methods of training them
US9227323B1 (en) * 2013-03-15 2016-01-05 Google Inc. Methods and systems for recognizing machine-readable information on three-dimensional objects
US20150019391A1 (en) * 2013-06-26 2015-01-15 Amazon Technologies, Inc. Detecting item interaction and movement
US20150081090A1 (en) * 2013-09-13 2015-03-19 JSC-Echigo Pte Ltd Material handling system and method
US9082071B2 (en) 2013-11-26 2015-07-14 Canon Kabushiki Kaisha Material classification using object/material interdependence with feedback
US20170225199A1 (en) * 2014-08-13 2017-08-10 Metrosense Oy Method, apparatus and system for sorting waste
US20170121113A1 (en) * 2015-09-11 2017-05-04 Berkshire Grey Inc. Robotic systems and methods for identifying and processing a variety of objects
US20170080566A1 (en) * 2015-09-21 2017-03-23 Amazon Technologies, Inc. Networked robotic manipulators
US20170126972A1 (en) * 2015-10-30 2017-05-04 Essential Products, Inc. Imaging device and method for generating an undistorted wide view image
US20170174440A1 (en) * 2015-12-16 2017-06-22 Waste Repurposing International, Inc. Household Hazardous Waste Recovery
US9639535B1 (en) * 2015-12-16 2017-05-02 Waste Repurposing International, Inc. Waste identification systems and methods
US10322506B2 (en) * 2016-05-06 2019-06-18 Kindred Systems Inc. Systems, devices, articles, and methods for using trained robots
US20170355078A1 (en) * 2016-06-09 2017-12-14 Shmuel Ur Innovation Ltd. System, Method and Product for Utilizing Prediction Models of an Environment
US10059005B2 (en) * 2016-06-22 2018-08-28 Quanta Storage Inc. Method for teaching a robotic arm to pick or place an object
US20170369244A1 (en) * 2016-06-27 2017-12-28 Amazon Technologies, Inc. Automated item singulation

Non-Patent Citations (13)

* Cited by examiner, † Cited by third party
Title
Almaddah, A. et al., "Visual and Physical Segmentation of Novel Objects", IEEE/RJS International Conference on Intelligent Robots and Systems, 807-812 (Sep. 2011).
Canadian Office Action for corresponding Canadian Patent Application No. 2,974,869 dated Sep. 29, 2017, 6 pages.
Chang, L. et al., "Interactive singulation of objects from a pile", IEEE International Conference on Robotics and Automation, 3875-3882 (May 2012).
Extended European Search Report for European Patent Application No. 17836465.9 dated Dec. 10, 2019, 11 pages.
Finnish Search Report for corresponding Finnish Patent Application No. 20165603 dated Nov. 18, 2016, 1 page.
Guttormsen, E. et al., "A Machine Vision System for Robust Sorting of Herring Fractions", Food and Bioprocess Technology, 9(11): 1893-1900 (Jul. 2016).
Kujala, J. et al., "Picking a Conveyor Clean by an Autonomously Learning Robot", retrieved from the Internet: http://arxiv.org/pdf/1511.07608v1.pdf, 6 pages (Nov. 2015).
Levine, S. et al., "Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection", www.arxiv.org, reference arXiv:1603.02199, 12 pages (2016).
Lukka, T. et al. "ZenRobotics Recycler-Robotic Sorting using Machine Learing", retrieved from Internet: https://users.ics.aalto.fi/praiko/oapers/SB14.pdf, 8 pages (Mar. 2014).
Lukka, T. et al. "ZenRobotics Recycler—Robotic Sorting using Machine Learing", retrieved from Internet: https://users.ics.aalto.fi/praiko/oapers/SB14.pdf, 8 pages (Mar. 2014).
Monouchehri, H. et al., "Sorting: Possibilities, Limitations and Future", Conference in Minerals Engineering, 1-17 (Feb. 2003).
Scavino, E. et al., "Application of automated image analysis to the identification and extraction of recyclable plastic bottles", Journal of Zhejiang University Science A., 10(6): 794-799 (Jun. 2009).
Selver, A. et al., "An automated industrial conveyor belt system using image processing and hierarchical clustering for classifying marble slabs", Robotics and Computer Integrated Manufacturing, 27(1): 164-176 (Feb. 2011).

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210187735A1 (en) * 2018-05-02 2021-06-24 X Development Llc Positioning a Robot Sensor for Object Classification
US11922368B1 (en) * 2020-12-11 2024-03-05 Amazon Technologies, Inc. Object classification exception handling via machine learning

Also Published As

Publication number Publication date
US11682097B2 (en) 2023-06-20
FI20165603A (fi) 2017-11-15
CA2974869C (en) 2019-06-11
JP2019533570A (ja) 2019-11-21
US20210110504A1 (en) 2021-04-15
AU2017305864A1 (en) 2019-03-07
WO2018024944A1 (en) 2018-02-08
US20180036774A1 (en) 2018-02-08
JP6868684B2 (ja) 2021-05-12
CA2974869A1 (en) 2017-10-25
FI127100B (fi) 2017-11-15
EP3493925A4 (en) 2020-01-08
EP3493925A1 (en) 2019-06-12

Similar Documents

Publication Publication Date Title
US11682097B2 (en) Method and an apparatus for separating at least one object from a plurality of objects
JP7522829B2 (ja) システム、方法及びコンピュータプログラム製品
US11850633B2 (en) Robotic system having shuttle
WO2018096902A1 (ja) ピッキングシステム及びその制御方法
JP6643921B2 (ja) 仕分装置および物品取出方法
JP2022160552A (ja) 動的動き調節機構を有するロボットシステム及びそれを動作させる方法
Pavlichenko et al. Kittingbot: A mobile manipulation robot for collaborative kitting in automotive logistics
CN116728399A (zh) 具有物体处理的机器人系统的系统和方法
Tavares et al. Flexible pick and place architecture using ROS framework
Lim et al. Human-robot collaboration and safety management for logistics and manipulation tasks
CN114896798A (zh) 碰撞检测方法、控制方法、抓取系统及计算机存储介质
Poss et al. Perceptionbased intelligent materialhandling in industrial logistics environments
US20240351214A1 (en) Method for controlling a handling system and handling system
Ankit et al. Multi-agent Cooperative Framework for Autonomous Wall Construction
Cenev et al. Vision based event classification in robotic micromanipulation
CN116061192A (zh) 具有物体处理的机器人系统的系统和方法
KR20240014795A (ko) 물류창고에서 사물배치로봇을 이용한 물류 처리시스템 및 방법
CN117377559A (zh) 用于抓取稳定性的路径约束的自动生成

Legal Events

Date Code Title Description
AS Assignment

Owner name: ZENROBOTICS OY, FINLAND

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:LUKKA, TUOMAS;KUJALA, JANNE;SIGNING DATES FROM 20180321 TO 20180327;REEL/FRAME:045447/0801

STPP Information on status: patent application and granting procedure in general

Free format text: NON FINAL ACTION MAILED

STPP Information on status: patent application and granting procedure in general

Free format text: FINAL REJECTION MAILED

STPP Information on status: patent application and granting procedure in general

Free format text: ADVISORY ACTION MAILED

STPP Information on status: patent application and granting procedure in general

Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION

STPP Information on status: patent application and granting procedure in general

Free format text: NON FINAL ACTION MAILED

STPP Information on status: patent application and granting procedure in general

Free format text: FINAL REJECTION MAILED

STPP Information on status: patent application and granting procedure in general

Free format text: NOTICE OF ALLOWANCE MAILED -- APPLICATION RECEIVED IN OFFICE OF PUBLICATIONS

STPP Information on status: patent application and granting procedure in general

Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT VERIFIED

STCF Information on status: patent grant

Free format text: PATENTED CASE

AS Assignment

Owner name: GENIE INDUSTRIES BV, NETHERLANDS

Free format text: ASSET SALE AND PURCHASE AGREEMENT;ASSIGNOR:ZENROBOTICS OY;REEL/FRAME:061604/0825

Effective date: 20220905

AS Assignment

Owner name: MP ZENROBOTICS OY, FINLAND

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:GENIE INDUSTRIES B.V.;REEL/FRAME:062880/0325

Effective date: 20230227

FEPP Fee payment procedure

Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

MAFP Maintenance fee payment

Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1551); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

Year of fee payment: 4